CytoPred: a server for prediction and classification of cytokines.

Lata, Sneh and Raghava, G.P.S. (2008) CytoPred: a server for prediction and classification of cytokines. Protein engineering, design & selection : PEDS, 21 (4). pp. 279-282. ISSN 1741-0126

PDF raghava08.pdf - Published Version Restricted to Registered users only Download (400Kb) | Request a copy

Abstract

Cytokines are messengers of immune system. They are small secreted proteins that mediate and regulate the immune system, inflammation and hematopoiesis. Recent studies have revealed important roles played by the cytokines in adjuvants as therapeutic targets and in cancer therapy. In this paper, an attempt has been made to predict this important class of proteins and classify further them into families and subfamilies. A PSI-BLAST+Support Vector Machine-based hybrid approach is adopted to develop the prediction methods. CytoPred is capable of predicting cytokines with an accuracy of 98.29%. The overall accuracy of classification of cytokines into four families and further classification into seven subfamilies is 99.77 and 97.24%, respectively. It has been shown by comparison that CytoPred performs better than the already existing CTKPred. A user-friendly server CytoPred has been developed and available at http://www.imtech.res.in/raghava/cytopred.

Item Type:	Article
Additional Information:	Copyright of this article belongs to Oxford University Press
Uncontrolled Keywords:	cytokine/prediction/PSI-BLAST/SVM
Subjects:	Q Science > QH Natural history > QH301 Biology QH301 Biology
Depositing User:	Dr. K.P.S.Sengar
Date Deposited:	30 Nov 2011 09:49
Last Modified:	13 Dec 2011 17:16
URI:	http://crdd.osdd.net/open/id/eprint/613

Actions (login required)

View Item